© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14074
    Prev
    Next
    INDEX
    Explanations

    compassing folder

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to unusually long (multi‐syllable) tokens—i.e. long words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    0.33
    %
    0.32
    DU
    0.31
    AN
    0.31
    ANO
    0.30
    J
    0.30
    Ε
    0.29
    YOU
    0.29
    4
    0.29
    AND
    0.29
    POSITIVE LOGITS
     preclude
    0.31
     taki
    0.31
     მიმო
    0.30
     dará
    0.30
    工地
    0.30
     busque
    0.30
    <unused82>
    0.30
     вікісторінку
    0.30
    ಂತ್ರಿ
    0.30
     mieć
    0.29
    Activations Density 0.000%

    No Known Activations